linux-input.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
* [PATCH 1/2] ads7846: Make buffers in struct ser_req and struct ads7845_ser_req DMA save
@ 2011-05-05  6:51 Alexander Stein
  2011-05-05  6:51 ` [PATCH 2/2] ads7846: Remove unused variable from struct ads7845_ser_req Alexander Stein
  2011-05-05  9:06 ` [PATCH 1/2] ads7846: Make buffers in struct ser_req and struct ads7845_ser_req DMA save Jonathan Cameron
  0 siblings, 2 replies; 4+ messages in thread
From: Alexander Stein @ 2011-05-05  6:51 UTC (permalink / raw)
  To: linux-input@vger.kernel.org; +Cc: Dmitry Torokhov, Alexander Stein

req.sample needs its own cacheline otherwise accessing req.msg fetches
it in again.

Note: This effect doesn't occur if the underlying SPI driver doesn't use
DMA at all.

Signed-off-by: Alexander Stein <alexander.stein@systec-electronic.com>
---
This obsoletes the patch
[PATCH 1/2] ads7846: Make buffers in ads7846_read12_ser and ads7845_read12_ser DMA save

 drivers/input/touchscreen/ads7846.c |   12 ++++++++++--
 1 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/input/touchscreen/ads7846.c b/drivers/input/touchscreen/ads7846.c
index c24946f..ab51a8d 100644
--- a/drivers/input/touchscreen/ads7846.c
+++ b/drivers/input/touchscreen/ads7846.c
@@ -281,17 +281,25 @@ struct ser_req {
 	u8			command;
 	u8			ref_off;
 	u16			scratch;
-	__be16			sample;
 	struct spi_message	msg;
 	struct spi_transfer	xfer[6];
+	/*
+	 * DMA (thus cache coherency maintenance) requires the
+	 * transfer buffers to live in their own cache lines.
+	 */
+	__be16 sample ____cacheline_aligned;
 };
 
 struct ads7845_ser_req {
 	u8			command[3];
 	u8			pwrdown[3];
-	u8			sample[3];
 	struct spi_message	msg;
 	struct spi_transfer	xfer[2];
+	/*
+	 * DMA (thus cache coherency maintenance) requires the
+	 * transfer buffers to live in their own cache lines.
+	 */
+	u8 sample[3] ____cacheline_aligned;
 };
 
 static int ads7846_read12_ser(struct device *dev, unsigned command)
-- 
1.7.3.4


^ permalink raw reply related	[flat|nested] 4+ messages in thread

* [PATCH 2/2] ads7846: Remove unused variable from struct ads7845_ser_req
  2011-05-05  6:51 [PATCH 1/2] ads7846: Make buffers in struct ser_req and struct ads7845_ser_req DMA save Alexander Stein
@ 2011-05-05  6:51 ` Alexander Stein
  2011-05-05  9:06 ` [PATCH 1/2] ads7846: Make buffers in struct ser_req and struct ads7845_ser_req DMA save Jonathan Cameron
  1 sibling, 0 replies; 4+ messages in thread
From: Alexander Stein @ 2011-05-05  6:51 UTC (permalink / raw)
  To: linux-input@vger.kernel.org; +Cc: Dmitry Torokhov, Alexander Stein

Signed-off-by: Alexander Stein <alexander.stein@systec-electronic.com>
---
This obsolets the patch
[PATCH 2/2] ads7846: Remove unused variable from struct ads7845_ser_req

 drivers/input/touchscreen/ads7846.c |    1 -
 1 files changed, 0 insertions(+), 1 deletions(-)

diff --git a/drivers/input/touchscreen/ads7846.c b/drivers/input/touchscreen/ads7846.c
index ab51a8d..1de1c19 100644
--- a/drivers/input/touchscreen/ads7846.c
+++ b/drivers/input/touchscreen/ads7846.c
@@ -292,7 +292,6 @@ struct ser_req {
 
 struct ads7845_ser_req {
 	u8			command[3];
-	u8			pwrdown[3];
 	struct spi_message	msg;
 	struct spi_transfer	xfer[2];
 	/*
-- 
1.7.3.4


^ permalink raw reply related	[flat|nested] 4+ messages in thread

* Re: [PATCH 1/2] ads7846: Make buffers in struct ser_req and struct ads7845_ser_req DMA save
  2011-05-05  6:51 [PATCH 1/2] ads7846: Make buffers in struct ser_req and struct ads7845_ser_req DMA save Alexander Stein
  2011-05-05  6:51 ` [PATCH 2/2] ads7846: Remove unused variable from struct ads7845_ser_req Alexander Stein
@ 2011-05-05  9:06 ` Jonathan Cameron
  2011-05-05 16:15   ` Dmitry Torokhov
  1 sibling, 1 reply; 4+ messages in thread
From: Jonathan Cameron @ 2011-05-05  9:06 UTC (permalink / raw)
  To: Alexander Stein; +Cc: linux-input@vger.kernel.org, Dmitry Torokhov

On 05/05/11 07:51, Alexander Stein wrote:
> req.sample needs its own cacheline otherwise accessing req.msg fetches
> it in again.
> 
> Note: This effect doesn't occur if the underlying SPI driver doesn't use
> DMA at all.
I would say the comment is a bit obvious, but then you are fixing a bug
because it was wrong - so fair call.
> 
> Signed-off-by: Alexander Stein <alexander.stein@systec-electronic.com>
Acked-by: Jonathan Cameron <jic23@cam.ac.uk>
> ---
> This obsoletes the patch
> [PATCH 1/2] ads7846: Make buffers in ads7846_read12_ser and ads7845_read12_ser DMA save
> 
>  drivers/input/touchscreen/ads7846.c |   12 ++++++++++--
>  1 files changed, 10 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/input/touchscreen/ads7846.c b/drivers/input/touchscreen/ads7846.c
> index c24946f..ab51a8d 100644
> --- a/drivers/input/touchscreen/ads7846.c
> +++ b/drivers/input/touchscreen/ads7846.c
> @@ -281,17 +281,25 @@ struct ser_req {
>  	u8			command;
>  	u8			ref_off;
>  	u16			scratch;
> -	__be16			sample;
>  	struct spi_message	msg;
>  	struct spi_transfer	xfer[6];
> +	/*
> +	 * DMA (thus cache coherency maintenance) requires the
> +	 * transfer buffers to live in their own cache lines.
> +	 */
> +	__be16 sample ____cacheline_aligned;
>  };
>  
>  struct ads7845_ser_req {
>  	u8			command[3];
>  	u8			pwrdown[3];
> -	u8			sample[3];
>  	struct spi_message	msg;
>  	struct spi_transfer	xfer[2];
> +	/*
> +	 * DMA (thus cache coherency maintenance) requires the
> +	 * transfer buffers to live in their own cache lines.
> +	 */
> +	u8 sample[3] ____cacheline_aligned;
>  };
>  
>  static int ads7846_read12_ser(struct device *dev, unsigned command)


^ permalink raw reply	[flat|nested] 4+ messages in thread

* Re: [PATCH 1/2] ads7846: Make buffers in struct ser_req and struct ads7845_ser_req DMA save
  2011-05-05  9:06 ` [PATCH 1/2] ads7846: Make buffers in struct ser_req and struct ads7845_ser_req DMA save Jonathan Cameron
@ 2011-05-05 16:15   ` Dmitry Torokhov
  0 siblings, 0 replies; 4+ messages in thread
From: Dmitry Torokhov @ 2011-05-05 16:15 UTC (permalink / raw)
  To: Jonathan Cameron; +Cc: Alexander Stein, linux-input@vger.kernel.org

On Thu, May 05, 2011 at 10:06:30AM +0100, Jonathan Cameron wrote:
> On 05/05/11 07:51, Alexander Stein wrote:
> > req.sample needs its own cacheline otherwise accessing req.msg fetches
> > it in again.
> > 
> > Note: This effect doesn't occur if the underlying SPI driver doesn't use
> > DMA at all.
> I would say the comment is a bit obvious, but then you are fixing a bug
> because it was wrong - so fair call.
> > 
> > Signed-off-by: Alexander Stein <alexander.stein@systec-electronic.com>
> Acked-by: Jonathan Cameron <jic23@cam.ac.uk>

Both applied, thanks Alexander and Jonathan.

-- 
Dmitry

^ permalink raw reply	[flat|nested] 4+ messages in thread

end of thread, other threads:[~2011-05-05 16:15 UTC | newest]

Thread overview: 4+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2011-05-05  6:51 [PATCH 1/2] ads7846: Make buffers in struct ser_req and struct ads7845_ser_req DMA save Alexander Stein
2011-05-05  6:51 ` [PATCH 2/2] ads7846: Remove unused variable from struct ads7845_ser_req Alexander Stein
2011-05-05  9:06 ` [PATCH 1/2] ads7846: Make buffers in struct ser_req and struct ads7845_ser_req DMA save Jonathan Cameron
2011-05-05 16:15   ` Dmitry Torokhov

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).